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:e4350d345d97b56ca7b59dbc011925ec1904d8a564b4e38969c9579b074ff804
+oid sha256:8055db90f42fee5ed3a04f8e2f82f2876510daae17de39fe875dc329471e61cf
 size 98088784

last-checkpoint/global_step2200/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f1060e94951e0d67c00943dc4edbea8362f01e2f01bb68d4fa1ba11ed71156d
+size 73939813

last-checkpoint/global_step2200/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71661a76470b478ccccf3bda308d70a16e8ae9db2cc271f76dd76d4a62713fc6
+size 73939813

last-checkpoint/global_step2200/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d16da774dd7f995c64c6caa673ce58168a1f630f8346cbd75312c8c9a2b2cf9
+size 73939877

last-checkpoint/global_step2200/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89e8664fa3368d2f982c5479babbd2b7ee307bdf0958f7146c217647e8fc8f9d
+size 73939877

last-checkpoint/global_step2200/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66ec164f48cc4bd5b4861fb2d384a6c48499839b79f437cce1bf036c308d39a9
+size 564993061

last-checkpoint/latest

@@ -1 +1 @@
-global_step2150
+global_step2200

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:065a50993eba0212276345f76d8268040ff81f0b0379c2af74bb3ae5b3dc8bf1
+oid sha256:e81d62e7084ca001d1b5cf644cfb14536e6b97346952c448c742ddf57fdfd532
 size 15429

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42410dea9cc1279875fd58cdbd387af92a3e6d12f7e52ff497b959ac4ac2873f
+oid sha256:2fbd1513273647ca78d0008023b44139e2c7296dca68be405e8ac78d228abbc1
 size 15429

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84327cb94481f4aa330fcca0f3bb1121ad581d5beb94e2475a38bda5aca36760
+oid sha256:8c16cd7c380d569e002df1e71f0f529e14f27d80568e86d31f5a8d1771e9373b
 size 15429

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15a861189dd19e0aceec678d8a75cad82c965ce69f5363194a8cdd37ec6a9f5d
+oid sha256:6153717d2e01ca1307e5f348eacbcc24aa0e03b7db7c5495269681f9bf005b35
 size 15429

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e94beadc98ff451c6f6d2bc6f85a9bd66bfdf5599b86c4c582259ad51b083b3
+oid sha256:5679dfe58fa3fbbdb3e1a0809d381121926283b52435d66b1116026c505eae88
 size 1401

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
   "best_global_step": null,
-  "best_metric": 0.6448646187782288,
+  "best_metric": 0.6429578065872192,
   "best_model_checkpoint": null,
-  "epoch": 2.1077770973668097,
+  "epoch": 2.1567666870789957,
   "eval_steps": 50,
-  "global_step": 2150,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3362,6 +3362,84 @@
       "eval_samples_per_second": 126.061,
       "eval_steps_per_second": 15.766,
       "step": 2150
+    },
+    {
+      "epoch": 2.112676056338028,
+      "grad_norm": 0.2285437434911728,
+      "learning_rate": 6.931328443798657e-05,
+      "loss": 0.6572,
+      "step": 2155
+    },
+    {
+      "epoch": 2.1175750153092467,
+      "grad_norm": 0.2500860095024109,
+      "learning_rate": 6.914131464583541e-05,
+      "loss": 0.6692,
+      "step": 2160
+    },
+    {
+      "epoch": 2.1224739742804655,
+      "grad_norm": 0.19759610295295715,
+      "learning_rate": 6.896920362642637e-05,
+      "loss": 0.6458,
+      "step": 2165
+    },
+    {
+      "epoch": 2.127372933251684,
+      "grad_norm": 0.21674296259880066,
+      "learning_rate": 6.879695314846654e-05,
+      "loss": 0.6727,
+      "step": 2170
+    },
+    {
+      "epoch": 2.1322718922229025,
+      "grad_norm": 0.2496577352285385,
+      "learning_rate": 6.862456498209603e-05,
+      "loss": 0.68,
+      "step": 2175
+    },
+    {
+      "epoch": 2.137170851194121,
+      "grad_norm": 0.18467482924461365,
+      "learning_rate": 6.845204089887e-05,
+      "loss": 0.6643,
+      "step": 2180
+    },
+    {
+      "epoch": 2.14206981016534,
+      "grad_norm": 0.21966247260570526,
+      "learning_rate": 6.827938267174033e-05,
+      "loss": 0.646,
+      "step": 2185
+    },
+    {
+      "epoch": 2.1469687691365587,
+      "grad_norm": 0.2213132381439209,
+      "learning_rate": 6.810659207503745e-05,
+      "loss": 0.6713,
+      "step": 2190
+    },
+    {
+      "epoch": 2.151867728107777,
+      "grad_norm": 0.21932950615882874,
+      "learning_rate": 6.793367088445207e-05,
+      "loss": 0.6688,
+      "step": 2195
+    },
+    {
+      "epoch": 2.1567666870789957,
+      "grad_norm": 0.2251294106245041,
+      "learning_rate": 6.776062087701701e-05,
+      "loss": 0.6882,
+      "step": 2200
+    },
+    {
+      "epoch": 2.1567666870789957,
+      "eval_loss": 0.6429578065872192,
+      "eval_runtime": 15.4736,
+      "eval_samples_per_second": 126.602,
+      "eval_steps_per_second": 15.833,
+      "step": 2200
     }
   ],
   "logging_steps": 5,
@@ -3390,7 +3468,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1081578526120346e+18,
+  "total_flos": 1.1339850078916444e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null