Training in progress, step 3150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e16399a54feade86bfbf61a8556cd130e7f0cb7bcc816ba08b4856dddb7606a
+oid sha256:fbe06d2e5a216d82ee0da0b20f9f7d21412c095eb557fb12c23294e23f968f48
 size 29034840

last-checkpoint/global_step3150/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:c94f613ed352743a5caa2667f44390e0a8efe4b7cd193140c1a0752d7694d874
+size 43429616

last-checkpoint/global_step3150/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f45741aceeec45e586c845b570d6a1b2046eb8a114fb3bdbc2e82fa39abf926
+size 43429616

last-checkpoint/global_step3150/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8efccedc1fb1d1ce7a83c7572a454618367997a9f4159d660e2add9113094021
+size 43429616

last-checkpoint/global_step3150/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:a438525af3ef256146b2b160f30f0cb97e6b90f349667b9aa8e925a7f7b1e0b3
+size 43429616

last-checkpoint/global_step3150/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:281a26e358d9b17c197c48c2ae0a968e2da59326496f249cb7f83e8232ef30a0
+size 637299

last-checkpoint/global_step3150/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65df32237bfebf0fa592beec8e1e4c267976dbf7907532a46eb21a9345b10fac
+size 637171

last-checkpoint/global_step3150/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:039e6c13e3b222cdbb597c188657b75ea26ce47df30b29d835301e61700e88b1
+size 637171

last-checkpoint/global_step3150/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a9da893289b58af4423adf1a183e2d4cf555b333a8fc3cb9ac838f1b86a164
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step3100
+global_step3150

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:381f090b12cbb3fcce976bd2e72d07a7786154c2848cc881d75715648e7c4dc2
+oid sha256:f819cf2c7fe8719d427eaa6ec9775983252517a512a5eb46040621049bb676c6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4321dc1beb6c245d4a16a8fb2bed2ce2a40d89e5a9c611c4572f63a09523846c
+oid sha256:2a78180f5e29cd98437c35591ab402d42bd98c8a12a813c23dfdfe59b5a850b5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b79020117e301cd96518c9d1e3eb43a609bc85799f14bac63d9c572fc04cb89
+oid sha256:5f43520b5104ee75a59749a66f5367557a7f191243b389309b6acad668af81d2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5429623c7323b4a820ea3d76194bc456c2affeeb1f3af8978aec5aee11b2d1ef
+oid sha256:2c502c4157180ff49243cd3eeb13c063be673f3bf094a73b62e8315ca6f65442
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3b3f02f00a06f9630f63af0f9d2eac4db52dcd348e24cd0a92f7c194ed5add6
+oid sha256:92d808df676978a6f9d91297467f7bfe66e17e4ef2506a29d8194cecbb4c2b8a
 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": 0.9158050221565731,
+  "epoch": 0.930576070901034,
   "eval_steps": 50,
-  "global_step": 3100,
+  "global_step": 3150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5525,11 +5525,100 @@
       "eval_steps_per_second": 0.788,
       "num_input_tokens_seen": 32196176,
       "step": 3100
+    },
+    {
+      "epoch": 0.9172821270310192,
+      "grad_norm": 0.9733516483269293,
+      "learning_rate": 6.089119060218385e-05,
+      "loss": 0.2205,
+      "num_input_tokens_seen": 32247416,
+      "step": 3105
+    },
+    {
+      "epoch": 0.9187592319054653,
+      "grad_norm": 1.393227303687879,
+      "learning_rate": 6.077196381972482e-05,
+      "loss": 0.2161,
+      "num_input_tokens_seen": 32298088,
+      "step": 3110
+    },
+    {
+      "epoch": 0.9202363367799113,
+      "grad_norm": 1.0898822094479876,
+      "learning_rate": 6.065267277183767e-05,
+      "loss": 0.1846,
+      "num_input_tokens_seen": 32349768,
+      "step": 3115
+    },
+    {
+      "epoch": 0.9217134416543574,
+      "grad_norm": 1.613649982790536,
+      "learning_rate": 6.0533318170211584e-05,
+      "loss": 0.2246,
+      "num_input_tokens_seen": 32401136,
+      "step": 3120
+    },
+    {
+      "epoch": 0.9231905465288035,
+      "grad_norm": 1.3536108105978324,
+      "learning_rate": 6.041390072691495e-05,
+      "loss": 0.1909,
+      "num_input_tokens_seen": 32453424,
+      "step": 3125
+    },
+    {
+      "epoch": 0.9246676514032496,
+      "grad_norm": 4.434791836263956,
+      "learning_rate": 6.0294421154391013e-05,
+      "loss": 0.1651,
+      "num_input_tokens_seen": 32506104,
+      "step": 3130
+    },
+    {
+      "epoch": 0.9261447562776958,
+      "grad_norm": 1.518977363790944,
+      "learning_rate": 6.0174880165453714e-05,
+      "loss": 0.2352,
+      "num_input_tokens_seen": 32557496,
+      "step": 3135
+    },
+    {
+      "epoch": 0.9276218611521418,
+      "grad_norm": 22.226709781269058,
+      "learning_rate": 6.005527847328338e-05,
+      "loss": 0.1875,
+      "num_input_tokens_seen": 32609696,
+      "step": 3140
+    },
+    {
+      "epoch": 0.9290989660265879,
+      "grad_norm": 1.4067637855508932,
+      "learning_rate": 5.993561679142253e-05,
+      "loss": 0.1889,
+      "num_input_tokens_seen": 32661992,
+      "step": 3145
+    },
+    {
+      "epoch": 0.930576070901034,
+      "grad_norm": 1.2192858374169209,
+      "learning_rate": 5.981589583377154e-05,
+      "loss": 0.2069,
+      "num_input_tokens_seen": 32713824,
+      "step": 3150
+    },
+    {
+      "epoch": 0.930576070901034,
+      "eval_loss": 0.20293839275836945,
+      "eval_runtime": 19.3509,
+      "eval_samples_per_second": 3.101,
+      "eval_steps_per_second": 0.775,
+      "num_input_tokens_seen": 32713824,
+      "step": 3150
     }
   ],
   "logging_steps": 5,
   "max_steps": 6770,
-  "num_input_tokens_seen": 32196176,
+  "num_input_tokens_seen": 32713824,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -5544,7 +5633,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2124006796820480.0,
+  "total_flos": 2158149397381120.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null