Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a2738a48f1b099eccf8ce2d9bba5cd1b371fced487cb0c89b426af8c8c80399
+oid sha256:3303f426e144318027e9598cbb48b6d245a5a69596ca6ee36391d7560c744786
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4436065ecb6f5459344458b31db3e495ac8d3ea43fec19035827d84333d19e29
+oid sha256:b40a58229095130b05b13431fbc0c18ac662f9551983a3edc0c14ad886af5adc
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94e2226a4aef85c91c05d3fe4db3cbebaf5b15177b012e050e969574c0421612
+oid sha256:b1616564de35907b8dfd36dcba5f2eb4ba22ca7c72d6c9a86ae72b94e8f1ce1b
 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": 0.11286681715575621,
+  "epoch": 0.1504890895410083,
   "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": 24.931,
       "eval_steps_per_second": 12.465,
       "step": 150
+    },
+    {
+      "epoch": 0.12039127163280662,
+      "grad_norm": 10.469996452331543,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 9.801,
+      "step": 160
+    },
+    {
+      "epoch": 0.12791572610985705,
+      "grad_norm": 8.660905838012695,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 9.9174,
+      "step": 170
+    },
+    {
+      "epoch": 0.13544018058690746,
+      "grad_norm": 13.137166023254395,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 9.9567,
+      "step": 180
+    },
+    {
+      "epoch": 0.14296463506395787,
+      "grad_norm": 8.647281646728516,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 10.3212,
+      "step": 190
+    },
+    {
+      "epoch": 0.1504890895410083,
+      "grad_norm": 6.7195868492126465,
+      "learning_rate": 0.0,
+      "loss": 9.9168,
+      "step": 200
+    },
+    {
+      "epoch": 0.1504890895410083,
+      "eval_loss": 2.487018346786499,
+      "eval_runtime": 22.4527,
+      "eval_samples_per_second": 24.941,
+      "eval_steps_per_second": 12.471,
+      "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": 3.0189737062957056e+16,
+  "total_flos": 4.05743055446999e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null