Training in progress, epoch 2, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78d6ee2f3cbc4cdb6322476898ecd624062b3c89295c346cbe39f5dde5c2f1ca
+oid sha256:3e89cd6eb023a8692705065f92f0d5371ce91e0df62544eb097bf03d18a65d84
 size 98088784

last-checkpoint/global_step2700/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02b7fa48200a5a042da0464ddaf341e8d30efd19d0e7b003acd0e140fc773067
+size 73939813

last-checkpoint/global_step2700/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:772bd63266afa3802bdd244de18d28b742842cc53dec6c297b70d6eaac8e06b5
+size 73939813

last-checkpoint/global_step2700/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:974d834923240a6423062503234126d5259de91b219571e9a4e038fcc8cf1b1f
+size 73939877

last-checkpoint/global_step2700/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3537ad743b04b039461b68e9164c6804f256bfe23970460856f048a4790810c
+size 73939877

last-checkpoint/global_step2700/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c8843c00c3514b22c11b1cbcc95febc90df3000d919ac4c3992920b30483c41
+size 564993061

last-checkpoint/latest

@@ -1 +1 @@
-global_step2650
+global_step2700

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:848a3bab324e767a79a267a7d989130506e36a874e0e4127d7de190f8481ff36
+oid sha256:ede0b1fc36335323175e2edd53261702567c37590048e71947e3c426e85b5358
 size 15429

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20080be7211d83966edb6b3c0a1d6111047cd73e94f53eb27565c9307a2a212e
+oid sha256:4c225af08c27371f3ad7414b25e230715ecb3f8cb70b10c4259ad6c0fda5ccd6
 size 15429

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e203ff29a80c4fd7eec0f580181ca0e442129d3db97917e3c8f0d40bfecd90
+oid sha256:e88a43fa2cddcb58d4826c017c03a1d3e5471c2689be34ccc5b5029741e5921b
 size 15429

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c0a80ff898e8e7e6862710635ce5d434aff7f8563552950e7cbca15d4174c7f
+oid sha256:0df0f25af541c09f9f007e452faad4d72697d4a9c57c257b511f80692e8b902e
 size 15429

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3c1fb4651c4fe532f8496df418c3c94914ae6844908aef425566dd85e1002e1
+oid sha256:4eaf8009039a6f74bcd21b41a171fcf3e5ca003f7176f1eba8b4e8308150dea7
 size 1401

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
   "best_global_step": null,
-  "best_metric": 0.6307803988456726,
+  "best_metric": 0.6300840377807617,
   "best_model_checkpoint": null,
-  "epoch": 2.597672994488671,
+  "epoch": 2.6466625842008575,
   "eval_steps": 50,
-  "global_step": 2650,
+  "global_step": 2700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4142,6 +4142,84 @@
       "eval_samples_per_second": 125.519,
       "eval_steps_per_second": 15.698,
       "step": 2650
+    },
+    {
+      "epoch": 2.60257195345989,
+      "grad_norm": 0.2412237972021103,
+      "learning_rate": 5.170746606940992e-05,
+      "loss": 0.671,
+      "step": 2655
+    },
+    {
+      "epoch": 2.6074709124311086,
+      "grad_norm": 0.22563929855823517,
+      "learning_rate": 5.153028819149837e-05,
+      "loss": 0.6472,
+      "step": 2660
+    },
+    {
+      "epoch": 2.612369871402327,
+      "grad_norm": 0.21387755870819092,
+      "learning_rate": 5.135315006687393e-05,
+      "loss": 0.6689,
+      "step": 2665
+    },
+    {
+      "epoch": 2.6172688303735456,
+      "grad_norm": 0.21877914667129517,
+      "learning_rate": 5.117605351590485e-05,
+      "loss": 0.6697,
+      "step": 2670
+    },
+    {
+      "epoch": 2.6221677893447644,
+      "grad_norm": 0.236678346991539,
+      "learning_rate": 5.099900035853222e-05,
+      "loss": 0.6506,
+      "step": 2675
+    },
+    {
+      "epoch": 2.6270667483159826,
+      "grad_norm": 0.2781834602355957,
+      "learning_rate": 5.082199241425118e-05,
+      "loss": 0.6589,
+      "step": 2680
+    },
+    {
+      "epoch": 2.6319657072872014,
+      "grad_norm": 0.24861498177051544,
+      "learning_rate": 5.064503150209222e-05,
+      "loss": 0.6571,
+      "step": 2685
+    },
+    {
+      "epoch": 2.63686466625842,
+      "grad_norm": 0.2387225478887558,
+      "learning_rate": 5.046811944060252e-05,
+      "loss": 0.6723,
+      "step": 2690
+    },
+    {
+      "epoch": 2.641763625229639,
+      "grad_norm": 0.20970548689365387,
+      "learning_rate": 5.029125804782722e-05,
+      "loss": 0.6585,
+      "step": 2695
+    },
+    {
+      "epoch": 2.6466625842008575,
+      "grad_norm": 0.2293289601802826,
+      "learning_rate": 5.01144491412908e-05,
+      "loss": 0.6658,
+      "step": 2700
+    },
+    {
+      "epoch": 2.6466625842008575,
+      "eval_loss": 0.6300840377807617,
+      "eval_runtime": 15.5653,
+      "eval_samples_per_second": 125.857,
+      "eval_steps_per_second": 15.74,
+      "step": 2700
     }
   ],
   "logging_steps": 5,
@@ -4170,7 +4248,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3663956002574172e+18,
+  "total_flos": 1.3915592955642511e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null