Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0772e042aac1a9c55b60ccd6d80d0f99d6094d42cbcd09d3a3a5ef693519b7e5
+oid sha256:ab391cd3159a64c515fac630ad026776453e42dbb46c50eba5add826ea16c1e5
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79bfe32cf9c15b2cf1b8bdce11c95dde24e734e8330b25b28e56d45b07f5d7d4
+oid sha256:d0c0a5310bfd63b1fff8308ec1cacac869be025fbf2a371aed89e902f8869c2e
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dab4add9816e0578961e3800e4c0a695d1376c53f2735279c96375981672ed0
+oid sha256:2653fa26103127586994025063275770d818265c4b9d4080b9f9aa5f4ade624d
 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": 0.0004984519233534312,
+  "epoch": 0.0006390409273761939,
   "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": 1.0682,
       "step": 35
+    },
+    {
+      "epoch": 0.0005112327419009551,
+      "grad_norm": 6.669098377227783,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0346,
+      "step": 40
+    },
+    {
+      "epoch": 0.0005112327419009551,
+      "eval_loss": 0.6382724046707153,
+      "eval_runtime": 3123.7215,
+      "eval_samples_per_second": 10.547,
+      "eval_steps_per_second": 5.274,
+      "step": 40
+    },
+    {
+      "epoch": 0.0005751368346385745,
+      "grad_norm": 3.0916411876678467,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5079,
+      "step": 45
+    },
+    {
+      "epoch": 0.0006390409273761939,
+      "grad_norm": 9.174546241760254,
+      "learning_rate": 0.0,
+      "loss": 0.8168,
+      "step": 50
+    },
+    {
+      "epoch": 0.0006390409273761939,
+      "eval_loss": 0.6152881979942322,
+      "eval_runtime": 3124.7336,
+      "eval_samples_per_second": 10.543,
+      "eval_steps_per_second": 5.272,
+      "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": 8055644948004864.0,
+  "total_flos": 1.0313277927063552e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null