Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f61948bd9477ff18eb6118cc259d9c29f6078bb742ff6ed6d033cff14bf3a33
+oid sha256:9244623d7b1ece339f124db6424b28f9d8cded28a2d70430cce07fc0dd53aba8
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c42c4b4503d61a90c12f888872c38f25e78542f2ac88606839baa1ca7f129a
+oid sha256:e885cd7baa9416aafbac167a2cd7508eeb4c3ace5eed1015f8f48c7987fe957c
 size 41119636

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": 0.08724100327153762,
+  "epoch": 0.17448200654307525,
   "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": 42.872,
       "eval_steps_per_second": 21.657,
       "step": 5
+    },
+    {
+      "epoch": 0.10468920392584515,
+      "grad_norm": 14.639806747436523,
+      "learning_rate": 6e-05,
+      "loss": 30.0739,
+      "step": 6
+    },
+    {
+      "epoch": 0.12213740458015267,
+      "grad_norm": 17.775012969970703,
+      "learning_rate": 7e-05,
+      "loss": 34.9073,
+      "step": 7
+    },
+    {
+      "epoch": 0.1395856052344602,
+      "grad_norm": 18.824005126953125,
+      "learning_rate": 8e-05,
+      "loss": 28.7388,
+      "step": 8
+    },
+    {
+      "epoch": 0.15703380588876772,
+      "grad_norm": 23.813568115234375,
+      "learning_rate": 9e-05,
+      "loss": 32.9446,
+      "step": 9
+    },
+    {
+      "epoch": 0.17448200654307525,
+      "grad_norm": 26.320598602294922,
+      "learning_rate": 0.0001,
+      "loss": 27.4221,
+      "step": 10
+    },
+    {
+      "epoch": 0.17448200654307525,
+      "eval_loss": NaN,
+      "eval_runtime": 2.2646,
+      "eval_samples_per_second": 42.833,
+      "eval_steps_per_second": 21.637,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3298217215131648.0,
+  "total_flos": 6596434430263296.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null