Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59ef861020fc2c545d37b93fe3da9a5df44bc38bc8294f53e4761c47fe0b54ec
+oid sha256:2bcd1f99ca4639d5b7aeddd12e28d8ae4f66d17cb473b2d54aaeb23e2af3a90c
 size 46708280

last-checkpoint/global_step1220/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ad49aa0764581eb18dba5361c652635c87dd910c3ec584db7af66e0ea850eb
+size 35203941

last-checkpoint/global_step1220/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3df07287976a4ae0b3a6f366185192fae937f1a132311fc534bdd405e77802fd
+size 35203941

last-checkpoint/global_step1220/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:ed4b735fcb85fd83e7ed250f2192cc3b2e74a86ff1254c584c90e1170755aa9f
+size 35204005

last-checkpoint/global_step1220/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58543f4049c28a886ff21739d7917eb63cf2045ca1a0804d41ac22d0186f0d67
+size 35204005

last-checkpoint/global_step1220/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a37c86006de61d0be3b78586059e4d98ea657b269c132c722369e6e4bc65670f
+size 46865049

last-checkpoint/latest

@@ -1 +1 @@
-global_step1200
+global_step1220

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d2bd7dfa69f36b5cf850cd9410f86cc2181cec385a8f9e5311babb0fe0865fe
+oid sha256:814c0560f0064c72cb05d6fdabce12f4ea60678ef99ae76b35beb0a5b61a746f
 size 15429

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91730c940535f449a5703b1d97f92415999c49e1bcf4e4f2f480a357a7f839ce
+oid sha256:d55f786f89c825e7eccff5f5ad6f275ae339974e5fc7ca3adc2610c4ddc7dc29
 size 15429

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ba288defe7ae7069401e52dcaf43410bef5f897eca8da4d501e9e15160c2b41
+oid sha256:f1050cb4078b8fb421e9d7cd11460b4f8b3150009a89652c0ce835de2f415292
 size 15429

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:386df291e7445294847744ac5bc975d02e8cbe3d748292dcfaae40c896523259
+oid sha256:05a9ac1e1c4df9ca87b88219341350f97eb24cac74de6cbc9e039d0e0d106d3c
 size 15429

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01830d6a6e4b363a7484b09ff196f1e3fb9b43729e4f01d3432c57d9d582ee8b
+oid sha256:99c32e39d9113c7bbf215e86b059c76588bc6462dcc095622f3886bf1b72f7af
 size 1401

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
   "best_global_step": null,
-  "best_metric": 1.0456267595291138,
+  "best_metric": 1.0451515913009644,
   "best_model_checkpoint": null,
-  "epoch": 0.17083674413638467,
+  "epoch": 0.17368402320532442,
   "eval_steps": 20,
-  "global_step": 1200,
+  "global_step": 1220,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2168,6 +2168,42 @@
       "eval_samples_per_second": 512.638,
       "eval_steps_per_second": 16.021,
       "step": 1200
+    },
+    {
+      "epoch": 0.1715485639036196,
+      "grad_norm": 1.4823371171951294,
+      "learning_rate": 2.8734766443620955e-05,
+      "loss": 1.0662,
+      "step": 1205
+    },
+    {
+      "epoch": 0.17226038367085453,
+      "grad_norm": 1.2662029266357422,
+      "learning_rate": 2.8733780986581105e-05,
+      "loss": 1.0515,
+      "step": 1210
+    },
+    {
+      "epoch": 0.17297220343808947,
+      "grad_norm": 1.5725047588348389,
+      "learning_rate": 2.8732791017215324e-05,
+      "loss": 1.0703,
+      "step": 1215
+    },
+    {
+      "epoch": 0.17368402320532442,
+      "grad_norm": 1.4703493118286133,
+      "learning_rate": 2.8731796535835716e-05,
+      "loss": 1.0047,
+      "step": 1220
+    },
+    {
+      "epoch": 0.17368402320532442,
+      "eval_loss": 1.0451515913009644,
+      "eval_runtime": 194.8815,
+      "eval_samples_per_second": 512.614,
+      "eval_steps_per_second": 16.02,
+      "step": 1220
     }
   ],
   "logging_steps": 5,
@@ -2196,7 +2232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.878891379026821e+17,
+  "total_flos": 5.974615545851412e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null