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:c63fa72bc094ccea57bfeac0fe1a90fdc0567ba18d8d266729fe6a3413b73747
+oid sha256:39b6c9c29df9c2ac9c5285c32391e09cfbc72d7f70a2656e0115b2ef96a04e8d
 size 81576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc18bf77a3368a0c13ef373ba5f13c8bc3714216ce240217116276607ab5bd00
+oid sha256:be4113e44bbcd932c38d490379e5a67d31a173c54a336f1ab32996b8bb1f60dc
 size 173094

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": 0.08859357696567,
+  "epoch": 0.17718715393134,
   "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": 144.169,
       "eval_steps_per_second": 72.843,
       "step": 5
+    },
+    {
+      "epoch": 0.10631229235880399,
+      "grad_norm": 0.12167657166719437,
+      "learning_rate": 6e-05,
+      "loss": 10.8354,
+      "step": 6
+    },
+    {
+      "epoch": 0.12403100775193798,
+      "grad_norm": 0.11268478631973267,
+      "learning_rate": 7e-05,
+      "loss": 10.8366,
+      "step": 7
+    },
+    {
+      "epoch": 0.14174972314507198,
+      "grad_norm": 0.1419811248779297,
+      "learning_rate": 8e-05,
+      "loss": 10.8329,
+      "step": 8
+    },
+    {
+      "epoch": 0.15946843853820597,
+      "grad_norm": 0.11876291781663895,
+      "learning_rate": 9e-05,
+      "loss": 10.8353,
+      "step": 9
+    },
+    {
+      "epoch": 0.17718715393134,
+      "grad_norm": 0.11256567388772964,
+      "learning_rate": 0.0001,
+      "loss": 10.8336,
+      "step": 10
+    },
+    {
+      "epoch": 0.17718715393134,
+      "eval_loss": 10.83576488494873,
+      "eval_runtime": 0.6028,
+      "eval_samples_per_second": 157.588,
+      "eval_steps_per_second": 79.623,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1661098917888.0,
+  "total_flos": 3322197835776.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null