Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cf1d7a09d2353328d498ec50bef66acd786f74a56a120be9e75139a05df9564
+oid sha256:b2d8a3fc101c685bf4f8a65054d57ee94448e35d06df44004131220d72a92ed1
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c021a0ab14cc11fc930967a5f107bbd915a812db2a5f15afdfa408ecf4035d0c
+oid sha256:c7e7ee541c756bbb487640afb304593615be706892e339f624eb17a8825d7559
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d5081b267af95cf9f6203c3aaa67179c8d8bf336dbaefda7c27713282c1dbdc
+oid sha256:7a8fbdd40f7edc9d5266c41a92e911a33f810a381088729bf4c84d9fe8f8cfae
 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": 0.02771362586605081,
+  "epoch": 0.05542725173210162,
   "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": 35.627,
       "eval_steps_per_second": 17.813,
       "step": 3
+    },
+    {
+      "epoch": 0.03695150115473441,
+      "grad_norm": 2.6365671157836914,
+      "learning_rate": 8e-05,
+      "loss": 2.9142,
+      "step": 4
+    },
+    {
+      "epoch": 0.046189376443418015,
+      "grad_norm": 2.907968759536743,
+      "learning_rate": 0.0001,
+      "loss": 3.6055,
+      "step": 5
+    },
+    {
+      "epoch": 0.05542725173210162,
+      "grad_norm": 3.0383033752441406,
+      "learning_rate": 0.00012,
+      "loss": 3.7958,
+      "step": 6
+    },
+    {
+      "epoch": 0.05542725173210162,
+      "eval_loss": 3.9253804683685303,
+      "eval_runtime": 1.3655,
+      "eval_samples_per_second": 33.687,
+      "eval_steps_per_second": 16.844,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 150029199212544.0,
+  "total_flos": 312560831692800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null