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:ebfbc8205e61ffeb3cdd441b9812f5498ecb4deb2bac7465d220552acf30bf4e
+oid sha256:cefb85955ebe21feb53e8313ec6f31ea11a5c98984468c6ba034e961827f55ab
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79f865cd5a23b2b296762c72638cee2c2d58ce31d4cf0f3be51fb11e1e2d4d79
+oid sha256:d0047c0fbb836927a251fe50085241d44611a39e9b2ab866788b0375dda65f43
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:426900dc4576c7b69ffe288dfe5ab8d765b6f0781fda217e5145137633ca7b0d
+oid sha256:79f0c87175ad7dd5f1c336a34b23c6e46a6ffc018d8186fd704338823c5e4efe
 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": 0.3194888178913738,
+  "epoch": 0.42598509052183176,
   "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": 20.023,
       "eval_steps_per_second": 10.011,
       "step": 150
+    },
+    {
+      "epoch": 0.3407880724174654,
+      "grad_norm": 1.265449047088623,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 1.1214,
+      "step": 160
+    },
+    {
+      "epoch": 0.362087326943557,
+      "grad_norm": 1.5992355346679688,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 1.2369,
+      "step": 170
+    },
+    {
+      "epoch": 0.38338658146964855,
+      "grad_norm": 1.3271338939666748,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 1.0608,
+      "step": 180
+    },
+    {
+      "epoch": 0.40468583599574015,
+      "grad_norm": 1.452867865562439,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 1.0436,
+      "step": 190
+    },
+    {
+      "epoch": 0.42598509052183176,
+      "grad_norm": 1.2788019180297852,
+      "learning_rate": 0.0,
+      "loss": 1.0797,
+      "step": 200
+    },
+    {
+      "epoch": 0.42598509052183176,
+      "eval_loss": 1.058427333831787,
+      "eval_runtime": 9.8879,
+      "eval_samples_per_second": 20.024,
+      "eval_steps_per_second": 10.012,
+      "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": 4.820547768680448e+16,
+  "total_flos": 6.435312538484736e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null