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:bc9d24030de22bc166dd807ff7664702af238d9842b136f2ee11acd6843b1ec0
+oid sha256:c658024d354049cde63ad33cdfb35c9728bdea655f41830fc532ce87c012e036
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9645553c3e72dacadcbb9e69f4595bb25f3f5a9da10578cceedf2a8b9ab6663
+oid sha256:b0b03f7c376b8f655ef25e462bbe423aa3e7bf05e1f99f3e865d346629419fa4
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:488018e38b0aef54d7962685dbc5ba3fc357c8075681a5eb7e7927b19146b363
+oid sha256:01a2e63450525491316c9f6ae0788c5a4d8c954d8d70191402ce82472cf9080d
 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": 0.005578800557880056,
+  "epoch": 0.007152308407538533,
   "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": 0.5149,
       "step": 35
+    },
+    {
+      "epoch": 0.005721846726030827,
+      "grad_norm": 0.5504866242408752,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4772,
+      "step": 40
+    },
+    {
+      "epoch": 0.005721846726030827,
+      "eval_loss": 0.5107699036598206,
+      "eval_runtime": 326.5743,
+      "eval_samples_per_second": 9.015,
+      "eval_steps_per_second": 4.507,
+      "step": 40
+    },
+    {
+      "epoch": 0.006437077566784679,
+      "grad_norm": 0.49994632601737976,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5116,
+      "step": 45
+    },
+    {
+      "epoch": 0.007152308407538533,
+      "grad_norm": 0.47652333974838257,
+      "learning_rate": 0.0,
+      "loss": 0.508,
+      "step": 50
+    },
+    {
+      "epoch": 0.007152308407538533,
+      "eval_loss": 0.5095760822296143,
+      "eval_runtime": 327.094,
+      "eval_samples_per_second": 9.0,
+      "eval_steps_per_second": 4.5,
+      "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": 1.2577036887392256e+16,
+  "total_flos": 1.6229926277480448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null