Training in progress, step 2550, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51ba4cb036f96637ea50997962c817be8981b7c185736e25bcaea373e2187935
+oid sha256:1423743ef577d043d7175f7e7d833ad5439113f93d35aae3b6833a3cf0e1cb32
 size 29034840

last-checkpoint/global_step2550/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:f29a88ea5d9b70f23bfc7d8df4834f8ec9eb3984889b6eb41c4fc4e0dfe55520
+size 43429616

last-checkpoint/global_step2550/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38359757b3fbb8e96e3ff3913f5d0aa896569c07d080dd28fdfb26ae27ac5c3c
+size 43429616

last-checkpoint/global_step2550/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aa6a53eda7f26bba15fd86b7065e2ec7fab955a6a5a2721e0b2618778f45fe0
+size 43429616

last-checkpoint/global_step2550/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2004ed1d03646db619ab4a937a8568de4e2b1a108c0f28378de10e0a8693edf8
+size 43429616

last-checkpoint/global_step2550/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:459c71b1156c55fcd73acb65442792d22282e3260b89f66cdf8ad0815d56f457
+size 637299

last-checkpoint/global_step2550/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c42effbfd8441de135408f95c55462d6c1c4c8dd96b6417b67de471d2e95afcb
+size 637171

last-checkpoint/global_step2550/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:304c5ba32c89fec95d937699d77819f8e533af674d93476e22a507dac625cebf
+size 637171

last-checkpoint/global_step2550/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcaea5da1d1730a97458c88513e37f66edcf7420f14ca71eb82cab77a1de4424
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step2500
+global_step2550

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a97c73c15a2a5b2de7dc426a700b2053aee43809425431c513cc5e3aab6c2107
+oid sha256:0362dfd92e8da01e4a0deedcbd1c493b8162d5d1d84d5a4c1cd210c556f2cf9b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1296b339c1b16ab7e14352a269004d20ede428aef748283fb0a6650d62f58129
+oid sha256:e65c5adee1a22c5343e38495a6905880496fb22d5e3ec5b16b87aadb731969d2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:000b1637f5e73170f2337500a6a083df3a43d967d642b6c3a68f60deb6c3b960
+oid sha256:f8d8858483b0c6944d55621cc2633469e3e0d04c48b6671eee92d4abab2352c2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8bcb6e7802f6d888bc099642911087298cfb1adf7053a2d43a67192a53404ef
+oid sha256:ca42ef4f7a2f8c2285c4cf6cef585dcc0b132b21e8bb33d96d53b6db837f5e54
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be10edf7c6be9f43df78beaad8c1006d912dae1be4452d19b94e400653092195
+oid sha256:67937b6f5a5203cd96f4ea9c985d72d16ed7c92555e94021ae353606f325a9ea
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.1869634985923767,
   "best_model_checkpoint": "saves/CADICA_qwenvl_direction_then_DetectAndClassify_scale6/lora/sft/checkpoint-2350",
-  "epoch": 0.7385524372230429,
+  "epoch": 0.7533234859675036,
   "eval_steps": 50,
-  "global_step": 2500,
+  "global_step": 2550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4457,11 +4457,100 @@
       "eval_steps_per_second": 0.784,
       "num_input_tokens_seen": 25961056,
       "step": 2500
+    },
+    {
+      "epoch": 0.740029542097489,
+      "grad_norm": 3.4127573468108934,
+      "learning_rate": 7.452610450181865e-05,
+      "loss": 0.2843,
+      "num_input_tokens_seen": 26012232,
+      "step": 2505
+    },
+    {
+      "epoch": 0.741506646971935,
+      "grad_norm": 1.8065383217954118,
+      "learning_rate": 7.441960654426687e-05,
+      "loss": 0.2376,
+      "num_input_tokens_seen": 26064432,
+      "step": 2510
+    },
+    {
+      "epoch": 0.7429837518463811,
+      "grad_norm": 1.038286812818806,
+      "learning_rate": 7.431296289958735e-05,
+      "loss": 0.2464,
+      "num_input_tokens_seen": 26115856,
+      "step": 2515
+    },
+    {
+      "epoch": 0.7444608567208272,
+      "grad_norm": 1.3908978510260759,
+      "learning_rate": 7.4206174204015e-05,
+      "loss": 0.2793,
+      "num_input_tokens_seen": 26167176,
+      "step": 2520
+    },
+    {
+      "epoch": 0.7459379615952733,
+      "grad_norm": 1.785011959334391,
+      "learning_rate": 7.409924109465011e-05,
+      "loss": 0.2141,
+      "num_input_tokens_seen": 26219144,
+      "step": 2525
+    },
+    {
+      "epoch": 0.7474150664697193,
+      "grad_norm": 1.0393762543520273,
+      "learning_rate": 7.399216420945453e-05,
+      "loss": 0.2137,
+      "num_input_tokens_seen": 26271712,
+      "step": 2530
+    },
+    {
+      "epoch": 0.7488921713441654,
+      "grad_norm": 5.12895726872253,
+      "learning_rate": 7.388494418724789e-05,
+      "loss": 0.2177,
+      "num_input_tokens_seen": 26323656,
+      "step": 2535
+    },
+    {
+      "epoch": 0.7503692762186115,
+      "grad_norm": 9.06455667620907,
+      "learning_rate": 7.377758166770377e-05,
+      "loss": 0.2762,
+      "num_input_tokens_seen": 26375392,
+      "step": 2540
+    },
+    {
+      "epoch": 0.7518463810930576,
+      "grad_norm": 1.4100384205361678,
+      "learning_rate": 7.367007729134588e-05,
+      "loss": 0.2794,
+      "num_input_tokens_seen": 26426080,
+      "step": 2545
+    },
+    {
+      "epoch": 0.7533234859675036,
+      "grad_norm": 0.9925649690798728,
+      "learning_rate": 7.356243169954426e-05,
+      "loss": 0.2364,
+      "num_input_tokens_seen": 26477208,
+      "step": 2550
+    },
+    {
+      "epoch": 0.7533234859675036,
+      "eval_loss": 0.38712552189826965,
+      "eval_runtime": 19.0707,
+      "eval_samples_per_second": 3.146,
+      "eval_steps_per_second": 0.787,
+      "num_input_tokens_seen": 26477208,
+      "step": 2550
     }
   ],
   "logging_steps": 5,
   "max_steps": 6770,
-  "num_input_tokens_seen": 25961056,
+  "num_input_tokens_seen": 26477208,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -4476,7 +4565,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1712735614402560.0,
+  "total_flos": 1746750507581440.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null