Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b504aa3d4948a3c83abc06e9460a58e7e182d4a9d10be063f85d6e4f7353de0f
+oid sha256:c57e9413a9cb0030e4d75efb8587c81042bc4f0ee4d2bde2be50bb8d5980d7fd
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3461b9451a3b4cdf406324c477284cc2fe1576bc6eaab860db46d4a75fd71fe8
+oid sha256:fa5cff1c6ead9d7d6d43ceb5895ea89dc53bebac1ca1d84b9a87e7fe78774896
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61f388398ea994e40704f6497243bd60adc9aa3f265cb5542e356410fda11e77
+oid sha256:4362fcd5a37a292cbf977b943f0b3f947ac977ee861d18729b9f450b9c75768d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0009038730962172911,
+  "epoch": 0.0018077461924345822,
   "eval_steps": 3,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0001,
       "loss": 1.4489,
       "step": 5
+    },
+    {
+      "epoch": 0.0010846477154607492,
+      "grad_norm": 0.629414975643158,
+      "learning_rate": 0.00012,
+      "loss": 1.2502,
+      "step": 6
+    },
+    {
+      "epoch": 0.0010846477154607492,
+      "eval_loss": 1.4722851514816284,
+      "eval_runtime": 708.6755,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 6
+    },
+    {
+      "epoch": 0.0012654223347042075,
+      "grad_norm": 1.3326071500778198,
+      "learning_rate": 0.00014,
+      "loss": 1.8625,
+      "step": 7
+    },
+    {
+      "epoch": 0.0014461969539476657,
+      "grad_norm": 0.6978418827056885,
+      "learning_rate": 0.00016,
+      "loss": 1.0635,
+      "step": 8
+    },
+    {
+      "epoch": 0.001626971573191124,
+      "grad_norm": 1.8490407466888428,
+      "learning_rate": 0.00018,
+      "loss": 1.5742,
+      "step": 9
+    },
+    {
+      "epoch": 0.001626971573191124,
+      "eval_loss": 1.3525186777114868,
+      "eval_runtime": 708.6847,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 9
+    },
+    {
+      "epoch": 0.0018077461924345822,
+      "grad_norm": 2.7478888034820557,
+      "learning_rate": 0.0002,
+      "loss": 2.1121,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -72,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2794842929233920.0,
+  "total_flos": 5589685858467840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null