Training in progress, step 120, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b75563214330cadaad1e3ffa6541232fd677cede80a0e63c8e468ed04cff992f
+oid sha256:2a3951e3588da4d12a28e9c1f4f7ff09ae0987de1e9e0842aebec5e0c9cb9404
 size 28130688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0988cb8639ed1fa07e068fc6c23d69e5afcc2081ed4d12b98d3b8c71977d8de6
+oid sha256:d082f72679ad57bd0eee09f2ab2986fb84ba7847fa90ef843c2705e8b1e91719
 size 28684730

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9906b173df03663b222bd12a0e83af5aaa020a12d4ad3b4f49197437057c696b
+oid sha256:c8717e6db6dad3bdb0d92afa70b8fbe0c4677a2360eab813a627812a62061fd4
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7bf7c9d7fc97693b96ee7a514a4d88728c8624bc298bf36b68fd64703b6ce38
+oid sha256:b6c7dfa9863eadd74540b95922e8cee67d3b691b168a951cb8b3349087d7a629
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cba90fd12df41e2a3afe0aa9bdbcb01ea64e70a37cf6d3f1b6f819528d9eedb2
+oid sha256:e7596c043bb61ec6ab94f537047f856762fd577107f970ea392238fff0ea6ef1
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f677ceac78336a23596ad2dfff49115dd4f2798e6c718f3d9a417036aecc78d
+oid sha256:712dd66678ab2f0cf679625d414555daee92b448e39ad2db26b98722c1b424fc
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b66cb249efdcbeae07a93ab18308b0dad6ab1938b8cda1783930dd7ca16e400
+oid sha256:6bb08d77b3a8f33a22badf4599bdece3856ac2be5b489c3048c3951f5a13e4fd
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a32fc5b45250ceb9579d6cdb22a9de146f720394a5fb1a94da8455a621d02420
+oid sha256:d84262c7d232955fd6ce9f416c4b38411017050149a8346d4ddba5d641d0b78f
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdaa72ece53788894cbf7d690659103118093c50cbe7ebcc4ad29ce77864063c
+oid sha256:144141c670561050eb2f8450fb88edb4facad52016564e94dfc875ba7b564975
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e1077a981f60bb0c73ac0edeec6a361fda9845f8d5236c4bc77fda2663cf80d
+oid sha256:dbe39dd1e728e6b0298971fe77b09b4d43dbe6b288ac55d64a2318e60f21229e
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fce9536ff5f950cceb3fa69a1e2f266b5d6de86d1ea82239294fb327d0664db
+oid sha256:416b2ea21de930aef02b3dd806b882963de9b98a0a8d9ff11b933cd6bf4116bc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09467455621301775,
+  "epoch": 0.14201183431952663,
   "eval_steps": 20,
-  "global_step": 80,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,98 +11,142 @@
     {
       "epoch": 0.001183431952662722,
       "eval_loss": 6.91423225402832,
-      "eval_runtime": 2.4498,
-      "eval_samples_per_second": 613.117,
-      "eval_steps_per_second": 38.371,
+      "eval_runtime": 2.3595,
+      "eval_samples_per_second": 636.584,
+      "eval_steps_per_second": 39.839,
       "step": 1
     },
     {
       "epoch": 0.011834319526627219,
-      "grad_norm": 5216.0,
+      "grad_norm": 4016.0,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 6.7203,
+      "loss": 6.6987,
       "step": 10
     },
     {
       "epoch": 0.023668639053254437,
-      "grad_norm": 2816.0,
+      "grad_norm": 2384.0,
       "learning_rate": 3.2000000000000005e-05,
-      "loss": 6.7656,
+      "loss": 6.731,
       "step": 20
     },
     {
       "epoch": 0.023668639053254437,
-      "eval_loss": 6.7287516593933105,
-      "eval_runtime": 2.4132,
-      "eval_samples_per_second": 622.421,
-      "eval_steps_per_second": 38.953,
+      "eval_loss": 6.770394802093506,
+      "eval_runtime": 2.3718,
+      "eval_samples_per_second": 633.275,
+      "eval_steps_per_second": 39.632,
       "step": 20
     },
     {
       "epoch": 0.03550295857988166,
-      "grad_norm": 11584.0,
+      "grad_norm": 6144.0,
       "learning_rate": 4.8e-05,
-      "loss": 6.7176,
+      "loss": 6.7332,
       "step": 30
     },
     {
       "epoch": 0.047337278106508875,
-      "grad_norm": 3216.0,
+      "grad_norm": 3520.0,
       "learning_rate": 6.400000000000001e-05,
-      "loss": 6.5546,
+      "loss": 6.501,
       "step": 40
     },
     {
       "epoch": 0.047337278106508875,
-      "eval_loss": 6.605761528015137,
-      "eval_runtime": 2.4034,
-      "eval_samples_per_second": 624.936,
-      "eval_steps_per_second": 39.111,
+      "eval_loss": 6.59076452255249,
+      "eval_runtime": 2.3851,
+      "eval_samples_per_second": 629.744,
+      "eval_steps_per_second": 39.411,
       "step": 40
     },
     {
       "epoch": 0.05917159763313609,
-      "grad_norm": 13312.0,
+      "grad_norm": 9280.0,
       "learning_rate": 8e-05,
-      "loss": 6.494,
+      "loss": 6.5837,
       "step": 50
     },
     {
       "epoch": 0.07100591715976332,
-      "grad_norm": 4640.0,
+      "grad_norm": 4768.0,
       "learning_rate": 9.6e-05,
-      "loss": 6.6277,
+      "loss": 7.248,
       "step": 60
     },
     {
       "epoch": 0.07100591715976332,
-      "eval_loss": 6.516293525695801,
-      "eval_runtime": 4.5908,
-      "eval_samples_per_second": 327.175,
-      "eval_steps_per_second": 20.476,
+      "eval_loss": 7.2996826171875,
+      "eval_runtime": 2.4128,
+      "eval_samples_per_second": 622.511,
+      "eval_steps_per_second": 38.959,
       "step": 60
     },
     {
       "epoch": 0.08284023668639054,
-      "grad_norm": 2464.0,
+      "grad_norm": 4288.0,
       "learning_rate": 0.00011200000000000001,
-      "loss": 6.6372,
+      "loss": 7.4279,
       "step": 70
     },
     {
       "epoch": 0.09467455621301775,
-      "grad_norm": 6880.0,
+      "grad_norm": 4320.0,
       "learning_rate": 0.00012800000000000002,
-      "loss": 6.852,
+      "loss": 7.0818,
       "step": 80
     },
     {
       "epoch": 0.09467455621301775,
-      "eval_loss": 7.38748836517334,
-      "eval_runtime": 4.0154,
-      "eval_samples_per_second": 374.06,
-      "eval_steps_per_second": 23.41,
+      "eval_loss": 7.198533535003662,
+      "eval_runtime": 2.3911,
+      "eval_samples_per_second": 628.164,
+      "eval_steps_per_second": 39.313,
       "step": 80
+    },
+    {
+      "epoch": 0.10650887573964497,
+      "grad_norm": 3488.0,
+      "learning_rate": 0.000144,
+      "loss": 7.0218,
+      "step": 90
+    },
+    {
+      "epoch": 0.11834319526627218,
+      "grad_norm": 5056.0,
+      "learning_rate": 0.00016,
+      "loss": 7.4375,
+      "step": 100
+    },
+    {
+      "epoch": 0.11834319526627218,
+      "eval_loss": 7.641583442687988,
+      "eval_runtime": 2.4227,
+      "eval_samples_per_second": 619.959,
+      "eval_steps_per_second": 38.799,
+      "step": 100
+    },
+    {
+      "epoch": 0.1301775147928994,
+      "grad_norm": 1712.0,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 7.8192,
+      "step": 110
+    },
+    {
+      "epoch": 0.14201183431952663,
+      "grad_norm": 324.0,
+      "learning_rate": 0.000192,
+      "loss": 8.5739,
+      "step": 120
+    },
+    {
+      "epoch": 0.14201183431952663,
+      "eval_loss": 9.108259201049805,
+      "eval_runtime": 2.4234,
+      "eval_samples_per_second": 619.802,
+      "eval_steps_per_second": 38.789,
+      "step": 120
     }
   ],
   "logging_steps": 10,
@@ -122,7 +166,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 120313111117824.0,
+  "total_flos": 180282263076864.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b433df4d3e09d6773f7a5755f93133eba240b72df27a491192fd745e486859e
+oid sha256:a6c7e7c5f21dbcaedc62ce8e58ac8c381dfbca0f0f8847ff8493ecb68e799bc5
 size 6712