Training in progress, step 455, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c360e553d157936718cf6be990e147d21346274ac808e87443ceef418127fde4
+oid sha256:b043cd7a58160e6996c90fab1beb1517bb2613e4b0999b16dca09195ed9daad8
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de4659248af871d8a5bc8618f52c5ea1baa9d060fad262290330351318b749ff
+oid sha256:fa5d29c4411fdeb35a1244b024f4c5c0c57180230285a448b1e43fc79ce803fc
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:815ec9236e78d8ac2fa18b52a6a75f823894c470f485337750679c813cd4c0ba
+oid sha256:450d4f0e3a0bdbd8c489459f618a362a3c0456d0f149f06ab048c544e79c9d17
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c794fb315dbb1d737ad184da5b30abdc3101c9a540dba62326f5d08191ea2bdb
+oid sha256:4ef7e9caf74d940d149631b7d434e8f3ed3d9f20dbfe42784c1a25924da5d43b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5823358136525396,
+  "epoch": 0.5888062115820123,
   "eval_steps": 386,
-  "global_step": 450,
+  "global_step": 455,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3173,6 +3173,41 @@
       "learning_rate": 9.730493562858953e-05,
       "loss": 0.8234,
       "step": 450
+    },
+    {
+      "epoch": 0.5836298932384342,
+      "grad_norm": 0.8427807688713074,
+      "learning_rate": 9.729156660844017e-05,
+      "loss": 1.1023,
+      "step": 451
+    },
+    {
+      "epoch": 0.5849239728243287,
+      "grad_norm": 0.8546382188796997,
+      "learning_rate": 9.727816543440458e-05,
+      "loss": 0.886,
+      "step": 452
+    },
+    {
+      "epoch": 0.5862180524102232,
+      "grad_norm": 0.6701838970184326,
+      "learning_rate": 9.726473211559437e-05,
+      "loss": 0.7861,
+      "step": 453
+    },
+    {
+      "epoch": 0.5875121319961177,
+      "grad_norm": 1.010311245918274,
+      "learning_rate": 9.725126666114292e-05,
+      "loss": 1.0393,
+      "step": 454
+    },
+    {
+      "epoch": 0.5888062115820123,
+      "grad_norm": 0.8440571427345276,
+      "learning_rate": 9.72377690802055e-05,
+      "loss": 0.9959,
+      "step": 455
     }
   ],
   "logging_steps": 1,
@@ -3192,7 +3227,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.030717272621056e+17,
+  "total_flos": 5.0866141312057344e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null