Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56f3caadc09736ba65c31d95ad7a37962e319df9347f4475d1e6d8021f905799
+oid sha256:9cc89545303c18949c80b514edaddae7e84866cb623a18f98c413b46a1c9d4d7
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49723feaf1237cfd93131f4f05acea90bc7ec5ba0dc9978772d442bd29989570
+oid sha256:3bcbdedded29af27703691374a9e8cead9c5c687c0bfbef0d54c617b6a2a6aa0
 size 61926

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6531c8916f86bd320c333db637094a901014c8debcbdff46f9636557899cd575
+oid sha256:f5c14142dfa46f49a566546178fbf9bb75cb8ea3abe4d872b9fb0e81794f00f4
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96701f95a81e310809b51a6b2cd0e3d766b115273a84b53734b30ba2e9666c49
+oid sha256:1707e0d4ace56f38c459da3c06c617c019d432eebcd26c94637a7024d10c4043
 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": 0.001363268436075491,
+  "epoch": 0.002726536872150982,
   "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": 135.203,
       "eval_steps_per_second": 33.805,
       "step": 5
+    },
+    {
+      "epoch": 0.0016359221232905893,
+      "grad_norm": 0.03697334602475166,
+      "learning_rate": 6e-05,
+      "loss": 11.9357,
+      "step": 6
+    },
+    {
+      "epoch": 0.0019085758105056873,
+      "grad_norm": 0.04659397527575493,
+      "learning_rate": 7e-05,
+      "loss": 11.9412,
+      "step": 7
+    },
+    {
+      "epoch": 0.0021812294977207854,
+      "grad_norm": 0.03356407210230827,
+      "learning_rate": 8e-05,
+      "loss": 11.9415,
+      "step": 8
+    },
+    {
+      "epoch": 0.002453883184935884,
+      "grad_norm": 0.037583865225315094,
+      "learning_rate": 9e-05,
+      "loss": 11.9381,
+      "step": 9
+    },
+    {
+      "epoch": 0.002726536872150982,
+      "grad_norm": 0.030221182852983475,
+      "learning_rate": 0.0001,
+      "loss": 11.9351,
+      "step": 10
+    },
+    {
+      "epoch": 0.002726536872150982,
+      "eval_loss": 11.938981056213379,
+      "eval_runtime": 182.6671,
+      "eval_samples_per_second": 135.268,
+      "eval_steps_per_second": 33.821,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 119915151360.0,
+  "total_flos": 239830302720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null