Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06cd5e17bbb7fbda5a4075ced1319a709d185865d1cb1978889dbdba1d0625e4
+oid sha256:7993d762fed3377525b3dca09571a7373d1144aacd1d93aeb53d30d0dcd6d870
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b125aa85114c50bb399f2c48aad70fe293b4e4e44649968d47b0d7529a944c8
+oid sha256:0c5eb26aab6895b830a4a285c033c2a6bd39f3deb21acd63d31cee6b3ed6d9fd
 size 63974

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": 0.0258732212160414,
+  "epoch": 0.0517464424320828,
   "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": 433.651,
       "eval_steps_per_second": 216.825,
       "step": 5
+    },
+    {
+      "epoch": 0.031047865459249677,
+      "grad_norm": 0.009419039823114872,
+      "learning_rate": 6e-05,
+      "loss": 10.3789,
+      "step": 6
+    },
+    {
+      "epoch": 0.03622250970245795,
+      "grad_norm": 0.008845251984894276,
+      "learning_rate": 7e-05,
+      "loss": 10.3786,
+      "step": 7
+    },
+    {
+      "epoch": 0.04139715394566624,
+      "grad_norm": 0.008657239377498627,
+      "learning_rate": 8e-05,
+      "loss": 10.3804,
+      "step": 8
+    },
+    {
+      "epoch": 0.04657179818887452,
+      "grad_norm": 0.009278891608119011,
+      "learning_rate": 9e-05,
+      "loss": 10.3809,
+      "step": 9
+    },
+    {
+      "epoch": 0.0517464424320828,
+      "grad_norm": 0.00981900468468666,
+      "learning_rate": 0.0001,
+      "loss": 10.3792,
+      "step": 10
+    },
+    {
+      "epoch": 0.0517464424320828,
+      "eval_loss": 10.379738807678223,
+      "eval_runtime": 0.7511,
+      "eval_samples_per_second": 434.044,
+      "eval_steps_per_second": 217.022,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 517236326400.0,
+  "total_flos": 1034472652800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null