Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eb5ef02054fe6d5b6ad94361f6a9d37e1849eaed62acbeacdbebda3d47ef183
+oid sha256:0ff36eb3d2516a384fbfb422bace62dc7ca67f797bdc0cc998e0f8a0f6007eb0
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2ede01753810014c5b9b897ddbc7b094c231159da1b0bd3ed03d3e51aa6cb09
+oid sha256:67e9ad62b95b6f6a324dcba070d6effc994bc6cf851f35048819b872f01b1e6c
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c7633efe974756db7301c844f23469d02329a219d6f8c0666f65a51b0de3d8
+oid sha256:1d1ed5fad87a528d3c6cf04d6bfca9c7875aa13a653f327bbb9dd8082b242c6f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005317154640580797,
+  "epoch": 0.006816864923821535,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 1.7511,
       "step": 35
+    },
+    {
+      "epoch": 0.005453491939057227,
+      "grad_norm": 0.7873528599739075,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.867,
+      "step": 40
+    },
+    {
+      "epoch": 0.005453491939057227,
+      "eval_loss": 1.862397313117981,
+      "eval_runtime": 106.5274,
+      "eval_samples_per_second": 28.997,
+      "eval_steps_per_second": 14.503,
+      "step": 40
+    },
+    {
+      "epoch": 0.006135178431439381,
+      "grad_norm": 0.9941609501838684,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.765,
+      "step": 45
+    },
+    {
+      "epoch": 0.006816864923821535,
+      "grad_norm": 0.7951815128326416,
+      "learning_rate": 0.0,
+      "loss": 1.953,
+      "step": 50
+    },
+    {
+      "epoch": 0.006816864923821535,
+      "eval_loss": 1.8610470294952393,
+      "eval_runtime": 106.8155,
+      "eval_samples_per_second": 28.919,
+      "eval_steps_per_second": 14.464,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1605641315549184.0,
+  "total_flos": 2068691432767488.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null