Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:288d7e326e8cb7e5762836aa874df4a0de5deb161f6c4630f54a6f10601dc327
+oid sha256:628fa114efbdc209508007e11d42fde209c5eb874335c46f0a33087ef72028cf
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e3f3ec8e51bad779c820c017916cfe3201d8b7b59b943142acb4d30ed4779fe
+oid sha256:5a9e96e11af229cd7f04dc268a161f5c152aaf2fad77fb70bf42852c34b1affc
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78b7e88f3e63922c4a8b6becd1b3734bda56290048e0c530af00ba5ba1620647
+oid sha256:e20e6cf25df1a73c081a325508521e0a139527415aa1406a7206400010e5059a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3a68034a6fca5f7c1565a9344e41aadbdff3752a8799ae94336c8c84c6d63d
+oid sha256:fa0fde01e60897f55f4ebaca5a490a1a483a2c53b2ae8e7543860a62c5b3298c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005528973950026581,
+  "epoch": 0.011057947900053162,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,105 @@
       "eval_samples_per_second": 11.013,
       "eval_steps_per_second": 5.507,
       "step": 13
+    },
+    {
+      "epoch": 0.005954279638490165,
+      "grad_norm": 0.4119487404823303,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.9006,
+      "step": 14
+    },
+    {
+      "epoch": 0.006379585326953748,
+      "grad_norm": 0.3977135419845581,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 0.9069,
+      "step": 15
+    },
+    {
+      "epoch": 0.006804891015417331,
+      "grad_norm": 0.45003339648246765,
+      "learning_rate": 4.72751631047092e-05,
+      "loss": 0.9576,
+      "step": 16
+    },
+    {
+      "epoch": 0.007230196703880914,
+      "grad_norm": 0.40881747007369995,
+      "learning_rate": 4.6316004108852305e-05,
+      "loss": 0.7697,
+      "step": 17
+    },
+    {
+      "epoch": 0.007655502392344498,
+      "grad_norm": 0.5239385962486267,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.8861,
+      "step": 18
+    },
+    {
+      "epoch": 0.00808080808080808,
+      "grad_norm": 0.4427054822444916,
+      "learning_rate": 4.401014914000078e-05,
+      "loss": 0.8403,
+      "step": 19
+    },
+    {
+      "epoch": 0.008506113769271665,
+      "grad_norm": 0.4336467683315277,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.8088,
+      "step": 20
+    },
+    {
+      "epoch": 0.008931419457735247,
+      "grad_norm": 0.46326103806495667,
+      "learning_rate": 4.123620120825459e-05,
+      "loss": 0.7963,
+      "step": 21
+    },
+    {
+      "epoch": 0.00935672514619883,
+      "grad_norm": 0.4596688449382782,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 0.7968,
+      "step": 22
+    },
+    {
+      "epoch": 0.009782030834662414,
+      "grad_norm": 0.4667969346046448,
+      "learning_rate": 3.8062464117898724e-05,
+      "loss": 0.8305,
+      "step": 23
+    },
+    {
+      "epoch": 0.010207336523125997,
+      "grad_norm": 0.3937626779079437,
+      "learning_rate": 3.634976249348867e-05,
+      "loss": 0.7507,
+      "step": 24
+    },
+    {
+      "epoch": 0.01063264221158958,
+      "grad_norm": 0.41750970482826233,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 0.785,
+      "step": 25
+    },
+    {
+      "epoch": 0.011057947900053162,
+      "grad_norm": 0.415423721075058,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.8375,
+      "step": 26
+    },
+    {
+      "epoch": 0.011057947900053162,
+      "eval_loss": 0.7622473239898682,
+      "eval_runtime": 89.8141,
+      "eval_samples_per_second": 11.023,
+      "eval_steps_per_second": 5.511,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7994668713246720.0,
+  "total_flos": 1.591018229071872e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null