Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fba06d676f14fe71702449fe62227001b586a6b7ced988777c27b81c83e435e
+oid sha256:fe13ad495e5185c6f2ade9dea5064a0301446ec00cdc0104021182123f09a79e
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1164985cea68a655b21dddb69d7462da48493044475e6b3548b9d9fc27d3a312
+oid sha256:aa5ec159a50343f73b499173ac045bbfe96a8bddcaf2f2f9b241030cceb6e036
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
+oid sha256:52c1e8dd4ba9ace9e6fcca937683862f29cfd6bf4fb3642d8d44c9c9a4359dc1
 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": 0.06927175843694494,
+  "epoch": 0.08880994671403197,
   "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": 10.3748,
       "step": 35
+    },
+    {
+      "epoch": 0.07104795737122557,
+      "grad_norm": 0.05530121922492981,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3747,
+      "step": 40
+    },
+    {
+      "epoch": 0.07104795737122557,
+      "eval_loss": 10.37551498413086,
+      "eval_runtime": 1.2478,
+      "eval_samples_per_second": 190.729,
+      "eval_steps_per_second": 95.364,
+      "step": 40
+    },
+    {
+      "epoch": 0.07992895204262877,
+      "grad_norm": 0.05178322643041611,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.364,
+      "step": 45
+    },
+    {
+      "epoch": 0.08880994671403197,
+      "grad_norm": 0.05107550323009491,
+      "learning_rate": 0.0,
+      "loss": 10.3756,
+      "step": 50
+    },
+    {
+      "epoch": 0.08880994671403197,
+      "eval_loss": 10.375503540039062,
+      "eval_runtime": 1.2205,
+      "eval_samples_per_second": 195.007,
+      "eval_steps_per_second": 97.503,
+      "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": 504305418240.0,
+  "total_flos": 646545408000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null