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:f37676b9dfb8bb4a61bb048c738f0bc6efc74424d4b083862c0fcd15a7460ec0
+oid sha256:925ae7edd08e4c4dd9e169aca529a75f1e10671710b3947404e3185d0c73dd7c
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:855046130e6406e7426e420db8b92cd8613e26ba40b18b5d755ac4a313b8a710
+oid sha256:d7c4af503ebb4e4ad7e5f88d37e306a196a1779f912363fa8219da8bfd791fa5
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2fb8dc2a85d0cc09b3d729bf71a8da974bf095341dbe298d83978634de38d32
+oid sha256:982eb43f0b685032f5d229850fc4c6116b1560071673bb981b13063a46a6b3e1
 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": 0.028145229383619477,
+  "epoch": 0.03752697251149264,
   "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": 323.443,
       "eval_steps_per_second": 161.721,
       "step": 150
+    },
+    {
+      "epoch": 0.030021578009194107,
+      "grad_norm": 0.07145528495311737,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 10.3517,
+      "step": 160
+    },
+    {
+      "epoch": 0.03189792663476874,
+      "grad_norm": 0.06188977509737015,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 10.3514,
+      "step": 170
+    },
+    {
+      "epoch": 0.03377427526034337,
+      "grad_norm": 0.06527094542980194,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 10.3527,
+      "step": 180
+    },
+    {
+      "epoch": 0.035650623885918005,
+      "grad_norm": 0.06538717448711395,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 10.3522,
+      "step": 190
+    },
+    {
+      "epoch": 0.03752697251149264,
+      "grad_norm": 0.051291242241859436,
+      "learning_rate": 0.0,
+      "loss": 10.352,
+      "step": 200
+    },
+    {
+      "epoch": 0.03752697251149264,
+      "eval_loss": 10.351256370544434,
+      "eval_runtime": 6.9459,
+      "eval_samples_per_second": 323.068,
+      "eval_steps_per_second": 161.534,
+      "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": 3701472460800.0,
+  "total_flos": 4949305098240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null