Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73b972f9bc64d410480b7739f47766d1d722fa0fc4e4ccc9fa6a3929f186e043
+oid sha256:9af965a03f4a1b4d0726aed83ed0af56fa7803d27d50f4de8cf215bf6004e4b5
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb8e2ae8bef2a763205ede29820fcfd849d175722e242b18c3c051600794f73f
+oid sha256:2a5e4942af8d3c6ac4b1ca5ab46ef98b6bc73bbb49efd7fa2f5a5d3ef8415201
 size 160284754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c99adfd3842a16f78adc954f43d1319a31e4bf74797a8fd450f6ab3f8c288b
+oid sha256:0c325a5b88aa7600e783ee566917eff9758a4ec707c33c129463258bf687aee2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:842484d97bbf42f9f92b7e7c8dcf4fda5e0b0607fec45e60ed168e6d3a7f3132
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03139717425431711,
+  "epoch": 0.04186289900575615,
   "eval_steps": 3,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,49 @@
       "eval_samples_per_second": 7.062,
       "eval_steps_per_second": 3.531,
       "step": 15
+    },
+    {
+      "epoch": 0.03349031920460492,
+      "grad_norm": 2.774341344833374,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.1482,
+      "step": 16
+    },
+    {
+      "epoch": 0.035583464154892726,
+      "grad_norm": 2.640618324279785,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.0841,
+      "step": 17
+    },
+    {
+      "epoch": 0.03767660910518053,
+      "grad_norm": 3.8104114532470703,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 2.4072,
+      "step": 18
+    },
+    {
+      "epoch": 0.03767660910518053,
+      "eval_loss": 0.510881245136261,
+      "eval_runtime": 28.714,
+      "eval_samples_per_second": 7.035,
+      "eval_steps_per_second": 3.517,
+      "step": 18
+    },
+    {
+      "epoch": 0.03976975405546834,
+      "grad_norm": 2.4819905757904053,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.8718,
+      "step": 19
+    },
+    {
+      "epoch": 0.04186289900575615,
+      "grad_norm": 3.231020212173462,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.3639,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -179,7 +222,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4886247726120960.0,
+  "total_flos": 6514996968161280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null