Training in progress, epoch 2, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c4f51fa6f911e049e780a696e42c197173adc1c720ea62553211b97093c7700
+oid sha256:714a0f64911c06cce5002cb0cee7d456626faa0e2be9dc2a5151f15eb1e465d1
 size 98088784

last-checkpoint/global_step2850/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:ac71ad5d37d39125b596393cc7fa653262c5853afc7fb764cda7f27e7cc8ec75
+size 73939813

last-checkpoint/global_step2850/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:910a6046a28dd371b4a32b4f21e6857719b440c4ac710df06df04ab810ecc72f
+size 73939813

last-checkpoint/global_step2850/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58110509c38fd1729820481028251014c1dc266b97a97c9606a30444f01d48ce
+size 73939877

last-checkpoint/global_step2850/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55bd7682bf7b2455f39090b66ec6d810f5f7594ef90cc9d19f302592bcc556cc
+size 73939877

last-checkpoint/global_step2850/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3716b6e924109aaed08b55fac9e2e907116865043e1c401001f3e60c0fbd28e
+size 564993061

last-checkpoint/latest

@@ -1 +1 @@
-global_step2800
+global_step2850

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a4fa1f6df963b1c19bf28f6d12dbde4a1b8ef0ca5a369f82c271f88aa3f5e3e
+oid sha256:c9d4ba51f2850c32bf4038fe8bb3f6c072a3c60df9dc486f70d1947f4041630e
 size 15429

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a77735fb4fd2d4aac8eb887c125af28b4f30ace97400e0ba9f3c0636ccc1d07f
+oid sha256:b244f2056e2d4c9f4346a38021a367743739a317ba64b88ae372d7e2c46609e5
 size 15429

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ee11e08f21a32477fca29bf02d692b330c7c6ccff2319eaab7535859efc55e4
+oid sha256:51dce82d5ef84280860f9f6ab9f2eaa72076762a5a40acf23250c9c3c7eeee5c
 size 15429

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46cac7155b9d7f9ac4851d59feed2bbb3fe391439f003a78f7d7f94e41cdb9fb
+oid sha256:bdef05f317c4bea0e8dbbe4eae5e4f217a0dba8b4a94a001ddd14f6abf877529
 size 15429

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dfa1f7eda7d25a9bf3aa4d73f1da5524a35718d7e994f9e5e9ea06ae60936fb
+oid sha256:d014abc04765b389bb4d14a91f1498560bbf81d8f2e53cbfd0e44890b0271e79
 size 1401

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
   "best_global_step": null,
-  "best_metric": 0.6278141736984253,
+  "best_metric": 0.6266533732414246,
   "best_model_checkpoint": null,
-  "epoch": 2.7446417636252294,
+  "epoch": 2.7936313533374157,
   "eval_steps": 50,
-  "global_step": 2800,
+  "global_step": 2850,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4376,6 +4376,84 @@
       "eval_samples_per_second": 127.173,
       "eval_steps_per_second": 15.905,
       "step": 2800
+    },
+    {
+      "epoch": 2.749540722596448,
+      "grad_norm": 0.2143499106168747,
+      "learning_rate": 4.641679873677696e-05,
+      "loss": 0.6653,
+      "step": 2805
+    },
+    {
+      "epoch": 2.754439681567667,
+      "grad_norm": 0.22827468812465668,
+      "learning_rate": 4.624160307134001e-05,
+      "loss": 0.6513,
+      "step": 2810
+    },
+    {
+      "epoch": 2.7593386405388856,
+      "grad_norm": 0.22044098377227783,
+      "learning_rate": 4.606650150861251e-05,
+      "loss": 0.6566,
+      "step": 2815
+    },
+    {
+      "epoch": 2.7642375995101043,
+      "grad_norm": 0.2288917750120163,
+      "learning_rate": 4.5891495848033936e-05,
+      "loss": 0.6823,
+      "step": 2820
+    },
+    {
+      "epoch": 2.7691365584813226,
+      "grad_norm": 0.20942112803459167,
+      "learning_rate": 4.571658788805822e-05,
+      "loss": 0.649,
+      "step": 2825
+    },
+    {
+      "epoch": 2.7740355174525413,
+      "grad_norm": 0.2301608920097351,
+      "learning_rate": 4.5541779426135283e-05,
+      "loss": 0.6647,
+      "step": 2830
+    },
+    {
+      "epoch": 2.77893447642376,
+      "grad_norm": 0.2222638577222824,
+      "learning_rate": 4.5367072258692513e-05,
+      "loss": 0.6538,
+      "step": 2835
+    },
+    {
+      "epoch": 2.7838334353949783,
+      "grad_norm": 0.2199936807155609,
+      "learning_rate": 4.519246818111638e-05,
+      "loss": 0.6449,
+      "step": 2840
+    },
+    {
+      "epoch": 2.788732394366197,
+      "grad_norm": 0.21400082111358643,
+      "learning_rate": 4.5017968987733936e-05,
+      "loss": 0.6706,
+      "step": 2845
+    },
+    {
+      "epoch": 2.7936313533374157,
+      "grad_norm": 0.2444697916507721,
+      "learning_rate": 4.484357647179441e-05,
+      "loss": 0.6756,
+      "step": 2850
+    },
+    {
+      "epoch": 2.7936313533374157,
+      "eval_loss": 0.6266533732414246,
+      "eval_runtime": 15.452,
+      "eval_samples_per_second": 126.779,
+      "eval_steps_per_second": 15.856,
+      "step": 2850
     }
   ],
   "logging_steps": 5,
@@ -4404,7 +4482,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4436686562978693e+18,
+  "total_flos": 1.4697431074728837e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null