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:adf259b2f2facea486819a41f491cec95cfde9f13f4eb534ace28ff34d339096
+oid sha256:2cc51fb6d2512cb36a3b23e155e7b3df71456eda31ed02c953ce7a24738b4dba
 size 684272496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bb0c38a296109b2604ec51629df68c51d264ddff30c574351f2f02781d039cf
+oid sha256:1a2aea5afb85a30fb8f24c02c2c3a736fd2ad3ac3b10391c3c6aeac430f24744
 size 81730196

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a305c8646024f3c572ea0ccfa07fad64529143504a930337d594faeae74ae0f
+oid sha256:bfb38c8d79b6f38bb790b1913bfdbc32aaa50622962ddeebd7fe86be4a71c506
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5947fce542ea9a5f31c6c5d7c4735173b40010f9fa5345cdd67f65a09485f538
+oid sha256:0e92f89ad47b97f18bdec3c5ec118ea00d4a1eb5574a7b3527978d8e4990243d
 size 14512

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": 0.013636751044063752,
+  "epoch": 0.027273502088127503,
   "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": 11.054,
       "eval_steps_per_second": 2.766,
       "step": 5
+    },
+    {
+      "epoch": 0.016364101252876503,
+      "grad_norm": 14.389070510864258,
+      "learning_rate": 6e-05,
+      "loss": 1.421,
+      "step": 6
+    },
+    {
+      "epoch": 0.01909145146168925,
+      "grad_norm": 8.234234809875488,
+      "learning_rate": 7e-05,
+      "loss": 0.6896,
+      "step": 7
+    },
+    {
+      "epoch": 0.021818801670502003,
+      "grad_norm": 4.542180061340332,
+      "learning_rate": 8e-05,
+      "loss": 0.3594,
+      "step": 8
+    },
+    {
+      "epoch": 0.02454615187931475,
+      "grad_norm": 3.838514804840088,
+      "learning_rate": 9e-05,
+      "loss": 0.2131,
+      "step": 9
+    },
+    {
+      "epoch": 0.027273502088127503,
+      "grad_norm": 1.6445430517196655,
+      "learning_rate": 0.0001,
+      "loss": 0.1487,
+      "step": 10
+    },
+    {
+      "epoch": 0.027273502088127503,
+      "eval_loss": 0.26161929965019226,
+      "eval_runtime": 223.4522,
+      "eval_samples_per_second": 11.054,
+      "eval_steps_per_second": 2.766,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0455337672900608e+17,
+  "total_flos": 2.0910675345801216e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null