Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07c1a59cf2b50a14ffff4e485a416293ddb928bf015dd55d7e06500c2e7a301b
+oid sha256:7d91a60a5f30f1a476b1f5e2574bd229ba7d919c2eb14e318433595981b458b3
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c984dd54e95b96e51a7f72f72b54150374bd192ae36ff230dafb61a22eeb9b5
+oid sha256:098e3ddbbb526dad6bcb198e106fad50376bcf0644e60eecb1e83b2992c83dd3
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff226c15e19b8085e09f0025aa31f4d46c591e213735b264a5e28d7f9728a70c
+oid sha256:6011dbc1beaf916a24aa0692a7ad3787fe62f4d3127d9859b27643438838594d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0014334605529574083,
+  "epoch": 0.0028669211059148166,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 121.011,
       "eval_steps_per_second": 60.516,
       "step": 5
+    },
+    {
+      "epoch": 0.00172015266354889,
+      "grad_norm": 1.7617462873458862,
+      "learning_rate": 6e-05,
+      "loss": 2.2562,
+      "step": 6
+    },
+    {
+      "epoch": 0.0020068447741403714,
+      "grad_norm": 1.7860451936721802,
+      "learning_rate": 7e-05,
+      "loss": 2.4667,
+      "step": 7
+    },
+    {
+      "epoch": 0.0022935368847318534,
+      "grad_norm": 1.786962628364563,
+      "learning_rate": 8e-05,
+      "loss": 2.3607,
+      "step": 8
+    },
+    {
+      "epoch": 0.002580228995323335,
+      "grad_norm": 1.9283440113067627,
+      "learning_rate": 9e-05,
+      "loss": 2.2896,
+      "step": 9
+    },
+    {
+      "epoch": 0.0028669211059148166,
+      "grad_norm": 1.9662737846374512,
+      "learning_rate": 0.0001,
+      "loss": 2.1083,
+      "step": 10
+    },
+    {
+      "epoch": 0.0028669211059148166,
+      "eval_loss": 2.109614610671997,
+      "eval_runtime": 48.5494,
+      "eval_samples_per_second": 121.011,
+      "eval_steps_per_second": 60.516,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 511583956500480.0,
+  "total_flos": 1029562712457216.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null