Training in progress, epoch 3, checkpoint

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ee5c23e36a220ddfb323d32d463c212f902254630a4ca1f579a0caca6ef359f
+oid sha256:4051c707e9d67cfe29ad210c13fe89896f2c3fc7cf4353ff0fb5017475ff87c2
 size 2692157

last-checkpoint/global_step1839/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40824c42ea14ffeefd7fc75cd0767d78e088e442096118184cd860122e366dfb
+size 1116913857

last-checkpoint/global_step1839/zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45f320f119d8b290b3be2c511810b2696c0144fca6384c664d24443c2feb1b97
+size 999614

last-checkpoint/global_step1839/zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:210158d4a933b97f035d06057819acb408cc38ea82d84bcbaa6243e46378d82a
+size 999614

last-checkpoint/global_step1839/zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4050ab88638e3a1c731aeb5de94a73c52d97d464a389d00feab9db01d92065b
+size 999614

last-checkpoint/global_step1839/zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:924a6351282a50ab0db8244df05142c7c75fb84fae16813815d76ad2ebe6b52a
+size 999614

last-checkpoint/global_step1839/zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdd4bbeedd997bdc8c69ce87b18768ce2ec7f18c9d29f66971da01ccc7c5f1a4
+size 999614

last-checkpoint/global_step1839/zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5554373702a027b6b6219676101faa9edc6278f11a98aa439f715e4c85eeef11
+size 999614

last-checkpoint/global_step1839/zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44f58b2871e135df7183956c33ee7549b753ca6637f8453873b8a7ca48213716
+size 999614

last-checkpoint/global_step1839/zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b8244a27d8c81a5b345b19ad02a8279ae5bfa5e0adf4fa97bbde27336042b7f
+size 999614

last-checkpoint/latest

@@ -1 +1 @@
-global_step1226
+global_step1839

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c31e33d70b3fe7f61d71a2b4a5353d94b31f406bedabb2083e35ac5bbc106208
+oid sha256:41c5681d7b524818ae5579d838cfcbe25ce71cbb169b0e4fe25d42c99edbaa8f
 size 21687

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38fe384dd20308f07ec5585d9912cb965830bcc11808cbdc846275b932905119
+oid sha256:271acd33082424567a4b8921da0385eeb19fdf6b335d06b40bad42f873f9cc25
 size 21687

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39ce95745d8ff40a4f8ee5a97f3689eaa9467213f9b27ce66ca594efc37198cf
+oid sha256:9ace92afd9705e6c007ccf569351131cf4a5b6d8ed4d24ab9a103d9a45bff8bd
 size 21687

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c349f517e129599281e2e4a383da6c74c212dfb7e6bad5c542f121cde888a562
+oid sha256:18546c9b491ceea5ed238dedef178d53954a71de51aba303b160c7cce45eef1f
 size 21687

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df27a56b73699e712acf3ed2a1bec8b4dc1f7438a81b82196f0c2f34f00b7551
+oid sha256:8b15878d0078501da1d9bbcc201adbc13f2502d53bc7ffcec18b7192e7f8278a
 size 21687

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34696be6d136ea03ea905aa2941fd96da980291d6b92db0de6b0a3b4d6447267
+oid sha256:6c88208606cc56bfd290ffae1a66345a8d63667df9957ad9300eb23e099a4a13
 size 21687

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0e2cbda44be671f5b71ae2543f2cec67328a527bccee980bbad52fe0ebf7dd5
+oid sha256:5b8dcfd13c9d761e6230bb5a862ca244f59def6f1d3abc7ceb716b463cb00455
 size 21687

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4070b9e9beda56664b5815d344e6c0f296840034807befc40392beac83c285b1
+oid sha256:a1ea431e317d84ef8ed752665a6947660d8675f81d803ed57c7af6c0c6638e06
 size 21687

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6314801573753357,
-  "best_model_checkpoint": "outputs/checkpoint-1226",
-  "epoch": 2.0,
+  "best_metric": 0.5994039177894592,
+  "best_model_checkpoint": "outputs/checkpoint-1839",
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 1226,
+  "global_step": 1839,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -167,13 +167,93 @@
       "eval_samples_per_second": 564.759,
       "eval_steps_per_second": 17.845,
       "step": 1226
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 4.5692926969522716e-05,
+      "loss": 0.7375,
+      "step": 1250
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 4.540540540540541e-05,
+      "loss": 0.7342,
+      "step": 1300
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 4.51178838412881e-05,
+      "loss": 0.7308,
+      "step": 1350
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 4.483036227717079e-05,
+      "loss": 0.7157,
+      "step": 1400
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 4.454284071305348e-05,
+      "loss": 0.7032,
+      "step": 1450
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 4.425531914893617e-05,
+      "loss": 0.7114,
+      "step": 1500
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 4.396779758481886e-05,
+      "loss": 0.7192,
+      "step": 1550
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 4.3680276020701557e-05,
+      "loss": 0.7132,
+      "step": 1600
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 4.339275445658424e-05,
+      "loss": 0.7106,
+      "step": 1650
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 4.310523289246694e-05,
+      "loss": 0.6874,
+      "step": 1700
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 4.281771132834963e-05,
+      "loss": 0.6983,
+      "step": 1750
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 4.253018976423232e-05,
+      "loss": 0.6989,
+      "step": 1800
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5994039177894592,
+      "eval_runtime": 2.0675,
+      "eval_samples_per_second": 566.385,
+      "eval_steps_per_second": 17.896,
+      "step": 1839
     }
   ],
   "logging_steps": 50,
   "max_steps": 9195,
   "num_train_epochs": 15,
   "save_steps": 500,
-  "total_flos": 2038462404362240.0,
+  "total_flos": 3058064064249856.0,
   "trial_name": null,
   "trial_params": null
 }