Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd1b77ccf8b42aa0e5ba9d469d890d8760d777f73ea4f48371d6a250ffabcf58
+oid sha256:6a255cc5ce734bbe23f23c79f2b4078f279af75615ab2654732ef205ac08c7d6
 size 63592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa2c7cf2d949340085056d6769de47512b761e4c311f420d9c7f1ac0ac3afd2a
+oid sha256:7a2e8ea15401435695a1a6d7c6fa2077b7252bf3b3dc816e830f3582c7ce4bad
 size 132798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1e9e72aa36a011dd8bb6eb4914d3ce04223a5c3d46913c8074bf89f9dd923bb
+oid sha256:1be0d95b349f4a5439b800db674fec71503f77dc49f4d60d939a137cc4996bad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
+oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.018409613909486065,
+  "epoch": 0.021477882894400408,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 485.988,
       "eval_steps_per_second": 60.785,
       "step": 54
+    },
+    {
+      "epoch": 0.019432370237790847,
+      "grad_norm": 0.4819900393486023,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 44.3073,
+      "step": 57
+    },
+    {
+      "epoch": 0.02045512656609563,
+      "grad_norm": 0.5234776735305786,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 44.3053,
+      "step": 60
+    },
+    {
+      "epoch": 0.021477882894400408,
+      "grad_norm": 0.5196526646614075,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 44.3021,
+      "step": 63
+    },
+    {
+      "epoch": 0.021477882894400408,
+      "eval_loss": 11.077031135559082,
+      "eval_runtime": 10.1496,
+      "eval_samples_per_second": 486.817,
+      "eval_steps_per_second": 60.889,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 404288962560.0,
+  "total_flos": 471670456320.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null