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:bed6dbe9a463afbdaa420d23f53fbeefe0bd5abe4bae29fe559d3f9cb28b9eab
+oid sha256:1b45ec95f0043d84a917be3d6f04955797c189083b11185c778f1d76d11b87c1
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbed3428b24e1c58e48c953eaea8913eb17ef0ed962516d13f3ea9bf5fa5c0c7
+oid sha256:195003e290ed8aeb00a1649608e4dfa74a795fe1218ab10c702a960b9b5bbcd0
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15a65fb9fd056a32de3901e991c48a566cc7007cf9d229006a3b1a882eda11f4
+oid sha256:4fc3a91f9269230182728d6fb293207d1ffd3c7378351159e969cb55058af9bd
 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": 0.1632208922742111,
+  "epoch": 0.2176278563656148,
   "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": 15.937,
       "eval_steps_per_second": 7.989,
       "step": 150
+    },
+    {
+      "epoch": 0.17410228509249184,
+      "grad_norm": 0.4978827238082886,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 0.3512,
+      "step": 160
+    },
+    {
+      "epoch": 0.18498367791077258,
+      "grad_norm": 0.42685166001319885,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.3719,
+      "step": 170
+    },
+    {
+      "epoch": 0.19586507072905332,
+      "grad_norm": 0.39568108320236206,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 0.3783,
+      "step": 180
+    },
+    {
+      "epoch": 0.20674646354733406,
+      "grad_norm": 0.6876519918441772,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 0.3972,
+      "step": 190
+    },
+    {
+      "epoch": 0.2176278563656148,
+      "grad_norm": 0.8734281659126282,
+      "learning_rate": 0.0,
+      "loss": 0.4679,
+      "step": 200
+    },
+    {
+      "epoch": 0.2176278563656148,
+      "eval_loss": 0.09196602553129196,
+      "eval_runtime": 24.2724,
+      "eval_samples_per_second": 15.944,
+      "eval_steps_per_second": 7.993,
+      "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": 4.511635400451686e+16,
+  "total_flos": 5.993797210708378e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null