Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55b9f2a309c2dfa6498c2bbcd70d7b66839b92909718c966f3f0721896295cd5
+oid sha256:beba287c1da9986499b08459f83b41439f8c2c5910097deaabda6d234640dfe9
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f561c7fd5dc1eb66bad195fded9117d1f4524dc58536212e129cf803d71e136f
+oid sha256:c2e25afba8d8c6d01b3222d0980f2915ef1f50b0c21fa7fc5b2e5aeeb7df6889
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:424f739be4501cfe7d354e89eb7c2636e769fe1c10cff142c347b71521f5cff2
+oid sha256:59dfd7e3c5f47e9c59dd82d5934b354dca1792ccd6d53d936783c3e96fc445c8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00022563601150743658,
+  "epoch": 0.00045127202301487317,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 59.038,
       "eval_steps_per_second": 29.524,
       "step": 3
+    },
+    {
+      "epoch": 0.0003008480153432488,
+      "grad_norm": 2.104339599609375,
+      "learning_rate": 8e-05,
+      "loss": 2.7221,
+      "step": 4
+    },
+    {
+      "epoch": 0.00037606001917906096,
+      "grad_norm": 1.4000215530395508,
+      "learning_rate": 0.0001,
+      "loss": 2.9295,
+      "step": 5
+    },
+    {
+      "epoch": 0.00045127202301487317,
+      "grad_norm": 2.1095762252807617,
+      "learning_rate": 0.00012,
+      "loss": 2.466,
+      "step": 6
+    },
+    {
+      "epoch": 0.00045127202301487317,
+      "eval_loss": 2.6572279930114746,
+      "eval_runtime": 96.0338,
+      "eval_samples_per_second": 58.302,
+      "eval_steps_per_second": 29.156,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 26711449141248.0,
+  "total_flos": 53422898282496.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null