Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c286dbdd22c4de2dedad335733f3787da58326340bb2381d2a636bb1a77fca2
+oid sha256:c2954eb4974667d2bf7a49870fd4add70717e75c536682949b066508b84f9c47
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d6bcc648ec3ecfeab36e24bd58429d9acdffbc26eaa5056f259d5a4ffe22c5d
+oid sha256:afd81c29576d4d412245a2a71e040b2f47e8003a3ea7249b7e7ee2d5090f8b15
 size 39398

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": 0.008107012565869477,
+  "epoch": 0.016214025131738953,
   "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": 670.837,
       "eval_steps_per_second": 335.741,
       "step": 5
+    },
+    {
+      "epoch": 0.009728415079043373,
+      "grad_norm": 0.016399100422859192,
+      "learning_rate": 6e-05,
+      "loss": 11.9391,
+      "step": 6
+    },
+    {
+      "epoch": 0.011349817592217268,
+      "grad_norm": 0.024656867608428,
+      "learning_rate": 7e-05,
+      "loss": 11.9368,
+      "step": 7
+    },
+    {
+      "epoch": 0.012971220105391163,
+      "grad_norm": 0.019521178677678108,
+      "learning_rate": 8e-05,
+      "loss": 11.9401,
+      "step": 8
+    },
+    {
+      "epoch": 0.014592622618565058,
+      "grad_norm": 0.02017282322049141,
+      "learning_rate": 9e-05,
+      "loss": 11.9355,
+      "step": 9
+    },
+    {
+      "epoch": 0.016214025131738953,
+      "grad_norm": 0.017548207193613052,
+      "learning_rate": 0.0001,
+      "loss": 11.9381,
+      "step": 10
+    },
+    {
+      "epoch": 0.016214025131738953,
+      "eval_loss": 11.933080673217773,
+      "eval_runtime": 1.6739,
+      "eval_samples_per_second": 620.723,
+      "eval_steps_per_second": 310.66,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2422308864.0,
+  "total_flos": 4844617728.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null