Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad34bd89979a395f5d20af9467f6aec91e83e1e56374f1307b1033dcc96df4c7
+oid sha256:947592abceaee94e3b3649532162aa930652dd816d55d57387a0e55cfe39d4e6
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aabe2dcdb398c9d63436f054cd285966182b2e2814011b259eb4985262d5b0f
+oid sha256:f7c6775b743b6e50d19681b49eb990663409152b4672b2c60ca0e5589cad641e
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d5081b267af95cf9f6203c3aaa67179c8d8bf336dbaefda7c27713282c1dbdc
+oid sha256:290db72453c0549da48ac2c903de9d8ef739ca7e660c6a1235dab2d77509f626
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006256517205422315,
+  "epoch": 0.01251303441084463,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 32.372,
       "eval_steps_per_second": 16.186,
       "step": 3
+    },
+    {
+      "epoch": 0.008342022940563087,
+      "grad_norm": 0.7793768644332886,
+      "learning_rate": 8e-05,
+      "loss": 2.1512,
+      "step": 4
+    },
+    {
+      "epoch": 0.010427528675703858,
+      "grad_norm": 0.7216593623161316,
+      "learning_rate": 0.0001,
+      "loss": 1.6963,
+      "step": 5
+    },
+    {
+      "epoch": 0.01251303441084463,
+      "grad_norm": 0.6446533799171448,
+      "learning_rate": 0.00012,
+      "loss": 1.6763,
+      "step": 6
+    },
+    {
+      "epoch": 0.01251303441084463,
+      "eval_loss": 1.991089940071106,
+      "eval_runtime": 6.3373,
+      "eval_samples_per_second": 31.875,
+      "eval_steps_per_second": 15.937,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 150029199212544.0,
+  "total_flos": 300058398425088.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null