Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f72eab8e82d4a3ebfaeeded13c0552334b26e14302a5161a2630c8bd5a24bd1a
+oid sha256:5152c60bb17a2b113ad1bcaad3ad6af5220501114ec2147800c39b5727d8db8d
 size 684272496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eccfb167eaa95d50bf83be9f2a408f5f20ddcabfc89c0c7b899facf90592dbe1
+oid sha256:ccbbf3c0db53eb1cba4ae34a5c5b6c6be81f166c7876a7bd5f4295d4d66e7817
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81d341293548ca00e0e58d5d96dd5b9a987f30f65d8d779264a3bcee6bef50b4
+oid sha256:e01c28df0e74f379f11a5bc69777121dc7b9c14b90ffd176758e1c14035ca1d5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07889546351084813,
+  "epoch": 0.09861932938856016,
   "eval_steps": 3,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,6 +203,57 @@
       "learning_rate": 5.000000000000002e-05,
       "loss": 0.209,
       "step": 20
+    },
+    {
+      "epoch": 0.08284023668639054,
+      "grad_norm": 1.0299311876296997,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.2146,
+      "step": 21
+    },
+    {
+      "epoch": 0.08284023668639054,
+      "eval_loss": 0.18857908248901367,
+      "eval_runtime": 22.4293,
+      "eval_samples_per_second": 9.541,
+      "eval_steps_per_second": 4.771,
+      "step": 21
+    },
+    {
+      "epoch": 0.08678500986193294,
+      "grad_norm": 0.6787167191505432,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.1958,
+      "step": 22
+    },
+    {
+      "epoch": 0.09072978303747535,
+      "grad_norm": 0.8082757592201233,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.2158,
+      "step": 23
+    },
+    {
+      "epoch": 0.09467455621301775,
+      "grad_norm": 1.5938321352005005,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.2725,
+      "step": 24
+    },
+    {
+      "epoch": 0.09467455621301775,
+      "eval_loss": 0.19068406522274017,
+      "eval_runtime": 22.3143,
+      "eval_samples_per_second": 9.59,
+      "eval_steps_per_second": 4.795,
+      "step": 24
+    },
+    {
+      "epoch": 0.09861932938856016,
+      "grad_norm": 0.9700214266777039,
+      "learning_rate": 0.0,
+      "loss": 0.1544,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -217,12 +268,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.613834418225152e+16,
+  "total_flos": 3.26729302278144e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null