Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:555ca7fddff4835e9496f5dbb37a348ac7f0c792ec702b751d80e8e7a30473e2
+oid sha256:c89b4cef26526fa730c9128e0343be6cd5a867c473fe87a78ea8a3a5ab96b237
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbf6f9996c2475a1000c53677c52308f25ede80a58cf1132b62ef40d7b881a7f
+oid sha256:a09438672de396517c7c6a2399f46b8db10a0522ccc5d3421e701c224c8350c5
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aa794c0dd0bdf630a8aff3083462d1c63bd52d0127d5fc99f733ac96352901e
+oid sha256:1b6c5bba5628b4cf51f881c0bc270cfaf83c59d7e3d517ade8699eeea1ab787a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0297000297000297,
+  "epoch": 0.0396000396000396,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 11.896,
       "eval_steps_per_second": 5.951,
       "step": 150
+    },
+    {
+      "epoch": 0.03168003168003168,
+      "grad_norm": 1.8827073574066162,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 3.3219,
+      "step": 160
+    },
+    {
+      "epoch": 0.03366003366003366,
+      "grad_norm": 1.6092329025268555,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 3.3611,
+      "step": 170
+    },
+    {
+      "epoch": 0.03564003564003564,
+      "grad_norm": 1.6704670190811157,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 3.8902,
+      "step": 180
+    },
+    {
+      "epoch": 0.03762003762003762,
+      "grad_norm": 1.419443964958191,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 3.5671,
+      "step": 190
+    },
+    {
+      "epoch": 0.0396000396000396,
+      "grad_norm": 1.2906014919281006,
+      "learning_rate": 0.0,
+      "loss": 3.1066,
+      "step": 200
+    },
+    {
+      "epoch": 0.0396000396000396,
+      "eval_loss": 0.8420388102531433,
+      "eval_runtime": 178.7659,
+      "eval_samples_per_second": 11.898,
+      "eval_steps_per_second": 5.952,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.3218937061376e+16,
+  "total_flos": 9.680730813628416e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null